readable AI benchmarks (simplified)
Anthropic
Claude 4.5 Haiku (Non-reasoning)
Claude 4.5 Haiku (Non-reasoning) has a Quality Score of 35.0, ranking 233rd among 571 scored models. Per 1M tokens, pricing is $1.00 input, $5.00 output, $0.100 cached input, and $1.25 cache write. It has a 200k token context window. Its Reliability Score is 46.2, ranking 167th among 573 scored models, above average (total average: 36.5). Its Value Score is 25.2, low compared with the total Value average of 31.4.
Quality Score35.0coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score25.2
Factual reliability46.2
Cache Discount90%
Model specification
- Reasoning
- non-reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 200k tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $1.00
- Output
- $5.00
- Cached Input
- $0.100
- Cache write
- $1.25
- Cost per task
- not available
Capability
- Intelligence
- 15.4
- Coding
- not available
- Agentic
- not available
- Omniscience
- -7.6
- Correct
- 14.4%
- Blended price
- $0.770
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 36.4%
Correct 14.4%Incorrect 22.0%Partial / not attempted 63.6%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 4%
- GPQA Diamond
- 65%
- CritPt
- 0%
- AA-Omniscience
- 46%
- AA-LCR
- 50%
Similar models
- Claude 3.7 Sonnet (Non-reasoning)AnthropicQuality Score 34.3Value Score 21.7
- Claude 4 Sonnet (Non-reasoning)AnthropicQuality Score 35.5Value Score not available
- Claude 4.5 Sonnet (Non-reasoning)AnthropicQuality Score 37.5Value Score 23.8
- Claude Sonnet 4.6 (Non-reasoning, Low)AnthropicQuality Score 42.4Value Score 26.8
- Claude Opus 4.5 (Non-reasoning)AnthropicQuality Score 42.2Value Score 25.2
- Claude Sonnet 5 (Non-reasoning, High)AnthropicQuality Score 42.7Value Score 28.3